Update README.md
Browse files
README.md
CHANGED
|
@@ -1,77 +1,12 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
```bash
|
| 14 |
-
https://github.com/wang-zhanyu/R2GenGPT.git
|
| 15 |
-
cd R2GenGPT
|
| 16 |
-
pip install -r requirements.txt
|
| 17 |
-
```
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
**2. Prepare the training dataset**
|
| 21 |
-
|
| 22 |
-
IU-xray: download the dataset from [here](https://drive.google.com/file/d/1c0BXEuDy8Cmm2jfN0YYGkQxFZd2ZIoLg/view)
|
| 23 |
-
|
| 24 |
-
Mimic-cxr: you can download our preprocess annotation file from [here](https://drive.google.com/file/d/14689ztodTtrQJYs--ihB_hgsPMMNHX-H/view?usp=sharing) and download the images from [official website](https://physionet.org/content/mimic-cxr-jpg/2.0.0/)
|
| 25 |
-
|
| 26 |
-
After downloading the data, place it in the ./data folder.
|
| 27 |
-
|
| 28 |
-
### Training
|
| 29 |
-
|
| 30 |
-
For shallow alignment
|
| 31 |
-
|
| 32 |
-
```bash
|
| 33 |
-
bash scripts/4-1.shallow_run.sh
|
| 34 |
-
```
|
| 35 |
-
|
| 36 |
-
For delta alignment
|
| 37 |
-
|
| 38 |
-
```bash
|
| 39 |
-
bash scripts/5-1.delta_run.sh
|
| 40 |
-
```
|
| 41 |
-
|
| 42 |
-
For deep alignment
|
| 43 |
-
|
| 44 |
-
```bash
|
| 45 |
-
bash scripts/6-1.deep_run.sh
|
| 46 |
-
```
|
| 47 |
-
|
| 48 |
-
### Testing (For MIMIC-CXR)
|
| 49 |
-
You can download our pretrained Delta checkpoints for [Here](https://drive.google.com/drive/folders/1ywEITWfYIAAYy0VY1IZ24Ec_GoNmkqIY?usp=sharing)
|
| 50 |
-
|
| 51 |
-
For shallow alignment
|
| 52 |
-
|
| 53 |
-
```bash
|
| 54 |
-
bash scripts/4-2.shallow_test.sh
|
| 55 |
-
```
|
| 56 |
-
|
| 57 |
-
For delta alignment
|
| 58 |
-
|
| 59 |
-
```bash
|
| 60 |
-
bash scripts/5-2.delta_test.sh
|
| 61 |
-
```
|
| 62 |
-
|
| 63 |
-
For deep alignment
|
| 64 |
-
|
| 65 |
-
```bash
|
| 66 |
-
bash scripts/6-2.shallow_test.sh
|
| 67 |
-
```
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
## Acknowledgement
|
| 71 |
-
|
| 72 |
-
+ [MiniGPT-4](https://github.com/Vision-CAIR/MiniGPT-4) Some codes of this repo are based on MiniGPT-4.
|
| 73 |
-
+ [Llama2](https://github.com/facebookresearch/llama) The fantastic language ability of Llama-2 with only 7B parameters is just amazing.
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
## License
|
| 77 |
-
This repository is under [BSD 3-Clause License](LICENSE.md).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: X RayDemo
|
| 3 |
+
emoji: 🏃
|
| 4 |
+
colorFrom: green
|
| 5 |
+
colorTo: green
|
| 6 |
+
sdk: streamlit
|
| 7 |
+
sdk_version: 1.35.0
|
| 8 |
+
app_file: app.py
|
| 9 |
+
pinned: false
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|